{"total":126,"rows":[{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","cited_by_count":96,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2511.07384","title":"Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence","created":"2025-11-10","cited_by_count":47,"area":"lr"},{"id":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2410.18517","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","created":"2024-10-24","cited_by_count":41,"area":"lr"},{"id":"2406.10594","title":"BlockPruner: Fine-grained Pruning for Large Language Models","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2405.18218","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2503.23798","title":"Adaptive Layer-skipping in Pre-trained LLMs","created":"2025-03-31","cited_by_count":27,"area":null},{"id":"2406.14833","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","created":"2024-06-21","cited_by_count":25,"area":null},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24,"area":null},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2410.19123","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","created":"2024-10-24","cited_by_count":19,"area":"moe"},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2501.15296","title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning","created":"2025-01-25","cited_by_count":17,"area":null},{"id":"2406.17415","title":"Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels","created":"2024-06-25","cited_by_count":16,"area":null},{"id":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2504.00502","title":"ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers","created":"2025-04-01","cited_by_count":14,"area":"mllm"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2407.06677","title":"Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules","created":"2024-07-09","cited_by_count":11,"area":null},{"id":"2409.13199","title":"CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information","created":"2024-09-20","cited_by_count":11,"area":null},{"id":"2506.04179","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2507.08064","title":"PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning","created":"2025-07-10","cited_by_count":11,"area":"distill"},{"id":"2407.00928","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2411.03513","title":"Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2606.06574","title":"Skip a Layer or Loop It? Learning Program-of-Layers in LLMs","created":"2026-06-04","cited_by_count":9,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2601.06787","title":"Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning","created":"2026-01-11","cited_by_count":8,"area":null},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2604.12358","title":"Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding","created":"2026-04-14","cited_by_count":7,"area":"mllm"},{"id":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"id":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2412.17560","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2501.00339","title":"GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression","created":"2024-12-31","cited_by_count":5,"area":null},{"id":"2501.02342","title":"Optimizing Small Language Models for In-Vehicle Function-Calling","created":"2025-01-04","cited_by_count":5,"area":"agents"},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.05005","title":"Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2505.23966","title":"FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression","created":"2025-05-29","cited_by_count":5,"area":"inference"},{"id":"2510.22228","title":"When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs","created":"2025-10-25","cited_by_count":5,"area":"lr"},{"id":"2601.21709","title":"Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis","created":"2026-01-29","cited_by_count":5,"area":"inference"},{"id":"2402.11819","title":"Head-wise Shareable Attention for Large Language Models","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2411.04530","title":"Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts?","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2412.18135","title":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","created":"2024-12-24","cited_by_count":4,"area":null},{"id":"2501.14713","title":"FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing","created":"2025-01-24","cited_by_count":4,"area":null},{"id":"2502.08690","title":"Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation","created":"2025-02-12","cited_by_count":4,"area":"diffusion"},{"id":"2503.09657","title":"T\\'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2409.09071","title":"Elastic On-Device LLM Service","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2501.11006","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2501.17905","title":"DReSS: Data-driven Regularized Structured Streamlining for Large Language Models","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2504.03794","title":"Entropy-Based Block Pruning for Efficient Large Language Models","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2505.18232","title":"Two-Stage Regularization-Based Structured Pruning for LLMs","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2505.20155","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2506.20480","title":"GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2511.02213","title":"IG-Pruning: Input-Guided Block Pruning for Large Language Models","created":"2025-11-04","cited_by_count":3,"area":null},{"id":"2601.19503","title":"GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2602.01997","title":"On the Limits of Layer Pruning for Generative Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2409.16302","title":"How Redundant Is the Transformer Stack in Speech Representation Models?","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2411.10272","title":"P$^2$ Law: Scaling Law for Post-Training After Model Pruning","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2411.14507","title":"From Pruning to Grafting: Dynamic Knowledge Redistribution via Learnable Layer Fusion","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2503.08524","title":"Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.04342","title":"Pruning Laws for Large Language Models","created":"2025-04-06","cited_by_count":2,"area":"moe"},{"id":"2508.08446","title":"OverFill: Two-Stage Models for Efficient Language Model Decoding","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2601.07212","title":"MI-PRUN: Optimize Large Language Model Pruning via Mutual Information","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.03295","title":"POP: Prefill-Only Pruning for Efficient Large Model Inference","created":"2026-02-03","cited_by_count":2,"area":"mllm"},{"id":"2602.08858","title":"FlattenGPT: Depth Compression for Transformer with Layer Flattening","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.07271","title":"Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.27786","title":"Locality-Aware Redundancy Pruning for LLM Depth Compression","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2406.08933","title":"LaCoOT: Layer Collapse through Optimal Transport","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2408.08684","title":"Research on Personalized Compression Algorithm for Pre-trained Models Based on Homomorphic Entropy Increase","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2408.13482","title":"MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruning","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2501.06126","title":"Merging Feed-Forward Sublayers for Compressed Transformers","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2503.06291","title":"IteRABRe: Iterative Recovery-Aided Block Reduction","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2504.08838","title":"SD$^2$: Self-Distilled Sparse Drafters","created":"2025-04-10","cited_by_count":1,"area":"inference"},{"id":"2505.03373","title":"SPAP: Structured Pruning via Alternating Optimization and Penalty Methods","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2506.02561","title":"Pruning General Large Language Models into Customized Expert Models","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2509.01221","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2510.13832","title":"Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.14649","title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2604.12247","title":"SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration","created":"2026-04-14","cited_by_count":1,"area":"inference"},{"id":"2604.19520","title":"SimDiff: Depth Pruning via Similarity and Difference","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.16234","title":"No Free Swap: Protocol-Dependent Layer Redundancy in Transformers","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.26861","title":"Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2608.19670","title":"The Asymmetric Harms of LLM Compression","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2609.31360","title":"Programs-of-Layers in LLMs through the Lens of Cortical Areas","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2409.05368","title":"Application Specific Compression of Deep Learning Models","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2410.06541","title":"Chip-Tuning: Classify Before Language Models Say","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2412.11494","title":"FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2504.03118","title":"NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2506.04513","title":"Pruning Everything, Everywhere, All at Once","created":"2025-06-04","cited_by_count":0,"area":null}],"next_cursor":"100"}